{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:AQZK7R4U5XMKEYD2LTXYG2IYS7","short_pith_number":"pith:AQZK7R4U","schema_version":"1.0","canonical_sha256":"0432afc794edd8a2607a5cef83691897ec40f6efdcf02bc8f28f18152c8d4c09","source":{"kind":"arxiv","id":"2102.08604","version":4},"attestation_state":"computed","paper":{"title":"SWAD: Domain Generalization by Seeking Flat Minima","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Han-Cheol Cho, Junbum Cha, Kyungjae Lee, Sanghyuk Chun, Seunghyun Park, Sungrae Park, Yunsung Lee","submitted_at":"2021-02-17T06:42:09Z","abstract_excerpt":"Domain generalization (DG) methods aim to achieve generalizability to an unseen target domain by using only training data from the source domains. Although a variety of DG methods have been proposed, a recent study shows that under a fair evaluation protocol, called DomainBed, the simple empirical risk minimization (ERM) approach works comparable to or even outperforms previous methods. Unfortunately, simply solving ERM on a complex, non-convex loss function can easily lead to sub-optimal generalizability by seeking sharp minima. In this paper, we theoretically show that finding flat minima re"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2102.08604","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-17T06:42:09Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"6aac9d2d789e42bb98dae2b73fd5950280b67c748a3d59ff454f33a2d234fab6","abstract_canon_sha256":"c46beec03dbc2613efa54980d13bad9cde0927756c01ce9d8bfc9848d53e70fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:28:36.493518Z","signature_b64":"EKmn5STICVvclvlNsR1wJwTFb9vQ65XDxfQWlTaiNoHIcPYn7muOYe+3JUAQ2Eas3VP+pORvWGFwb4w7jy2sCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0432afc794edd8a2607a5cef83691897ec40f6efdcf02bc8f28f18152c8d4c09","last_reissued_at":"2026-07-05T03:28:36.492895Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:28:36.492895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SWAD: Domain Generalization by Seeking Flat Minima","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Han-Cheol Cho, Junbum Cha, Kyungjae Lee, Sanghyuk Chun, Seunghyun Park, Sungrae Park, Yunsung Lee","submitted_at":"2021-02-17T06:42:09Z","abstract_excerpt":"Domain generalization (DG) methods aim to achieve generalizability to an unseen target domain by using only training data from the source domains. Although a variety of DG methods have been proposed, a recent study shows that under a fair evaluation protocol, called DomainBed, the simple empirical risk minimization (ERM) approach works comparable to or even outperforms previous methods. Unfortunately, simply solving ERM on a complex, non-convex loss function can easily lead to sub-optimal generalizability by seeking sharp minima. In this paper, we theoretically show that finding flat minima re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.08604","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2102.08604/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2102.08604","created_at":"2026-07-05T03:28:36.492973+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.08604v4","created_at":"2026-07-05T03:28:36.492973+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.08604","created_at":"2026-07-05T03:28:36.492973+00:00"},{"alias_kind":"pith_short_12","alias_value":"AQZK7R4U5XMK","created_at":"2026-07-05T03:28:36.492973+00:00"},{"alias_kind":"pith_short_16","alias_value":"AQZK7R4U5XMKEYD2","created_at":"2026-07-05T03:28:36.492973+00:00"},{"alias_kind":"pith_short_8","alias_value":"AQZK7R4U","created_at":"2026-07-05T03:28:36.492973+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.05564","citing_title":"TabICL: A Tabular Foundation Model for In-Context Learning on Large Data","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AQZK7R4U5XMKEYD2LTXYG2IYS7","json":"https://pith.science/pith/AQZK7R4U5XMKEYD2LTXYG2IYS7.json","graph_json":"https://pith.science/api/pith-number/AQZK7R4U5XMKEYD2LTXYG2IYS7/graph.json","events_json":"https://pith.science/api/pith-number/AQZK7R4U5XMKEYD2LTXYG2IYS7/events.json","paper":"https://pith.science/paper/AQZK7R4U"},"agent_actions":{"view_html":"https://pith.science/pith/AQZK7R4U5XMKEYD2LTXYG2IYS7","download_json":"https://pith.science/pith/AQZK7R4U5XMKEYD2LTXYG2IYS7.json","view_paper":"https://pith.science/paper/AQZK7R4U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.08604&json=true","fetch_graph":"https://pith.science/api/pith-number/AQZK7R4U5XMKEYD2LTXYG2IYS7/graph.json","fetch_events":"https://pith.science/api/pith-number/AQZK7R4U5XMKEYD2LTXYG2IYS7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AQZK7R4U5XMKEYD2LTXYG2IYS7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AQZK7R4U5XMKEYD2LTXYG2IYS7/action/storage_attestation","attest_author":"https://pith.science/pith/AQZK7R4U5XMKEYD2LTXYG2IYS7/action/author_attestation","sign_citation":"https://pith.science/pith/AQZK7R4U5XMKEYD2LTXYG2IYS7/action/citation_signature","submit_replication":"https://pith.science/pith/AQZK7R4U5XMKEYD2LTXYG2IYS7/action/replication_record"}},"created_at":"2026-07-05T03:28:36.492973+00:00","updated_at":"2026-07-05T03:28:36.492973+00:00"}